AQUAINT Workshop – June 2003 Improved Semantic Role Parsing Kadri Hacioglu, Sameer Pradhan, Valerie Krugler, Steven Bethard, Ashley Thornton, Wayne Ward,

Slides:



Advertisements
Similar presentations
Feature Forest Models for Syntactic Parsing Yusuke Miyao University of Tokyo.
Advertisements

 Christel Kemke 2007/08 COMP 4060 Natural Language Processing Feature Structures and Unification.
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
SEMANTIC ROLE LABELING BY TAGGING SYNTACTIC CHUNKS
1 Automatic Semantic Role Labeling Scott Wen-tau Yih Kristina Toutanova Microsoft Research Thanks to.
Sequence Classification: Chunking Shallow Processing Techniques for NLP Ling570 November 28, 2011.
E XTRACTING SEMANTIC ROLE INFORMATION FROM UNSTRUCTURED TEXTS Diana Trandab ă 1 and Alexandru Trandab ă 2 1 Faculty of Computer Science, University “Al.
Max-Margin Matching for Semantic Role Labeling David Vickrey James Connor Daphne Koller Stanford University.
Semantic Role Labeling Abdul-Lateef Yussiff
Probabilistic Parsing Chapter 14, Part 2 This slide set was adapted from J. Martin, R. Mihalcea, Rebecca Hwa, and Ray Mooney.
A Joint Model For Semantic Role Labeling Aria Haghighi, Kristina Toutanova, Christopher D. Manning Computer Science Department Stanford University.
Learning with Probabilistic Features for Improved Pipeline Models Razvan C. Bunescu Electrical Engineering and Computer Science Ohio University Athens,
Towards Parsing Unrestricted Text into PropBank Predicate- Argument Structures ACL4 Project NCLT Seminar Presentation, 7th June 2006 Conor Cafferkey.
LING 581: Advanced Computational Linguistics Lecture Notes January 19th.
Shallow Parsing CS 4705 Julia Hirschberg 1. Shallow or Partial Parsing Sometimes we don’t need a complete parse tree –Information extraction –Question.
Text Mining in Biomedicine Michael Krauthammer Department of Pathology Yale University School of Medicine.
Semantic Role Chunking Combining Complementary Syntactic Views Sameer Pradhan, Kadri Hacioglu, Wayne Ward, James H. Martin, Daniel Jurafsky  Center for.
Applications of Sequence Learning CMPT 825 Mashaal A. Memon
Introduction to treebanks Session 1: 7/08/
SRL using complete syntactic analysis Mihai Surdeanu and Jordi Turmo TALP Research Center Universitat Politècnica de Catalunya.
Two-Phase Semantic Role Labeling based on Support Vector Machines Kyung-Mi Park Young-Sook Hwang Hae-Chang Rim NLP Lab. Korea Univ.
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Shallow Parsing.
Extracting LTAGs from Treebanks Fei Xia 04/26/07.
Page 1 Generalized Inference with Multiple Semantic Role Labeling Systems Peter Koomen, Vasin Punyakanok, Dan Roth, (Scott) Wen-tau Yih Department of Computer.
Introduction to Syntax, with Part-of-Speech Tagging Owen Rambow September 17 & 19.
Probabilistic Parsing Ling 571 Fei Xia Week 5: 10/25-10/27/05.
Semantic Role Labeling using Maximum Entropy Model Joon-Ho Lim NLP Lab. Korea Univ.
ELN – Natural Language Processing Giuseppe Attardi
AQUAINT Kickoff Meeting – December 2001 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
Semantic Role Labeling
Automatic Extraction of Opinion Propositions and their Holders Steven Bethard, Hong Yu, Ashley Thornton, Vasileios Hatzivassiloglou and Dan Jurafsky Department.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Tree Kernels for Parsing: (Collins & Duffy, 2001) Advanced Statistical Methods in NLP Ling 572 February 28, 2012.
Probabilistic Parsing Reading: Chap 14, Jurafsky & Martin This slide set was adapted from J. Martin, U. Colorado Instructor: Paul Tarau, based on Rada.
PropBank, VerbNet & SemLink Edward Loper. PropBank 1M words of WSJ annotated with predicate- argument structures for verbs. –The location & type of each.
Ling 570 Day 17: Named Entity Recognition Chunking.
HW7 Extracting Arguments for % Ang Sun March 25, 2012.
CS : Language Technology for the Web/Natural Language Processing Pushpak Bhattacharyya CSE Dept., IIT Bombay Constituent Parsing and Algorithms (with.
Semantic Role Labeling for Arabic using Kernel Methods Mona Diab Alessandro Moschitti Daniele Pighin.
INSTITUTE OF COMPUTING TECHNOLOGY Forest-based Semantic Role Labeling Hao Xiong, Haitao Mi, Yang Liu and Qun Liu Institute of Computing Technology Academy.
CS774. Markov Random Field : Theory and Application Lecture 19 Kyomin Jung KAIST Nov
A Cascaded Finite-State Parser for German Michael Schiehlen Institut für Maschinelle Sprachverarbeitung Universität Stuttgart
Transformation-Based Learning Advanced Statistical Methods in NLP Ling 572 March 1, 2012.
Conversion of Penn Treebank Data to Text. Penn TreeBank Project “A Bank of Linguistic Trees” (as of 11/1992) University of Pennsylvania, LINC Laboratory.
Semantic Role Labeling. Introduction Semantic Role Labeling AgentThemePredicateLocation.
AQUAINT Phase II Six Month Workshop – October 2004 Fusing Rich Information Extracted from Multiple Media and Languages to Generate Contextualized, Complex.
Prototype-Driven Learning for Sequence Models Aria Haghighi and Dan Klein University of California Berkeley Slides prepared by Andrew Carlson for the Semi-
Introduction to Syntactic Parsing Roxana Girju November 18, 2004 Some slides were provided by Michael Collins (MIT) and Dan Moldovan (UT Dallas)
LING 001 Introduction to Linguistics Spring 2010 Syntactic parsing Part-Of-Speech tagging Apr. 5 Computational linguistics.
Supertagging CMSC Natural Language Processing January 31, 2006.
Shallow Parsing for South Asian Languages -Himanshu Agrawal.
11 Project, Part 3. Outline Basics of supervised learning using Naïve Bayes (using a simpler example) Features for the project 2.
NLP. Introduction to NLP Last week, Min broke the window with a hammer. The window was broken with a hammer by Min last week With a hammer, Min broke.
1 Fine-grained and Coarse-grained Word Sense Disambiguation Jinying Chen, Hoa Trang Dang, Martha Palmer August 22, 2003.
Multilinugual PennTools that capture parses and predicate-argument structures, for use in Applications Martha Palmer, Aravind Joshi, Mitch Marcus, Mark.
Open Health Natural Language Processing Consortium
Overview of Statistical NLP IR Group Meeting March 7, 2006.
LING/C SC 581: Advanced Computational Linguistics Lecture Notes Feb 3 rd.
AQUAINT Mid-Year PI Meeting – June 2002 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.
LING/C SC 581: Advanced Computational Linguistics Lecture Notes Feb 17 th.
Relation Extraction (RE) via Supervised Classification See: Jurafsky & Martin SLP book, Chapter 22 Exploring Various Knowledge in Relation Extraction.
LING 581: Advanced Computational Linguistics Lecture Notes March 2nd.
COSC 6336: Natural Language Processing
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
Parsing in Multiple Languages
Probabilistic and Lexicalized Parsing
LING/C SC 581: Advanced Computational Linguistics
CSCI 5832 Natural Language Processing
Towards comprehensive syntactic and semantic annotations of the clinical narrative Daniel Albright, Arrick Lanfranchi, Anwen Fredriksen, William F Styler.
Progress report on Semantic Role Labeling
Presentation transcript:

AQUAINT Workshop – June 2003 Improved Semantic Role Parsing Kadri Hacioglu, Sameer Pradhan, Valerie Krugler, Steven Bethard, Ashley Thornton, Wayne Ward, Dan Jurafsky, James Martin Center for Spoken Language Research University of Colorado Boulder, CO

AQUAINT Workshop – June 2003 What is Semantic Role Tagging? Assigning semantic labels to sentence elements. Elements are arguments of some predicate or participants in some event. –Who did What to Whom, How, When, Where, Why [ TEMPORAL In 1901 ] [ THEME President William McKinley ] [ TARGET was shot] [ AGENT by anarchist Leon Czolgosz ] [ LOCATION at the Pan-American Exposition ]

AQUAINT Workshop – June 2003 Parsing Algorithm From Gildea and Jurafsky (2002) Generate syntactic parse of sentence (Charniak) Specify predicate (verb) For each constituent node in parse tree: –Extract features relative to predicate Path, Voice, Headword, Position, Phrase Type, Sub-Cat –Estimate P(Role| features) for each role and normalize –Assign role with highest probability

AQUAINT Workshop – June 2003 SVM Classifier Same basic procedure as (Gildea & Jurafsky 2000) –Same features except include predicate as feature Change classification step to use SVM TinySVM software [Kudo & Matsumoto 2000] Prune constituents with P(Null) > 0.98 –For efficiency in training –Prunes ~ 80% of constituents For each role train one-vs-all classifier –Includes Null role

AQUAINT Workshop – June 2003 SVM Classification Generate syntactic parse (Charniak parser) For each target (verb) Prune constituents with P(Null) > 0.98 Run each ova classifier on remaining constituents Convert SVM output to probs by fitting sigmoid Described in Platt 2000 Generate N-best labels for each constituent Pick highest prob sequence of non-overlapping roles

AQUAINT Workshop – June 2003 Features Target word (verb) Cluster for target word (64) Path from cons to target Phrase Type Position (before/after) Voice Head Word Sub-categorization Path: NP S VP VB Head Word: He Sub-cat: VP VB NP

AQUAINT Workshop – June 2003 Role Labels Arg0 ArgM-ADV Arg1 ArgM-CAU Arg2 ArgM-DIR Arg3 ArgM-DIS Arg4 ArgM-EXT Arg5 ArgM-LOC ArgA ArgM-MNR ArgM ArgM-MOD ArgM-REC ArgM-NEG ArgM-PRD ArgM-PRP ArgM-TMP Agent Actor Beneficiary Cause Degree Experiencer Goal Instrument Location Manner Means Proposition Result State Stimulus Source Temporal Theme Topic Type Other PropBank ArgumentsThematic Roles

AQUAINT Workshop – June 2003 Data PropBank data –WSJ section of Penn TreeBank –Annotated with Predicate-Argument Train on PropBank Training Set –Section 00, 23 witheld – 72,000 annotated roles Test on PropBank section-23 –3,800 annotated roles

AQUAINT Workshop – June 2003 SVM Performance Arg ID P R F Role Assign SVM Surdeanu03 (same feat) Surdeanu03 (add’tl feat) Gildea & Palmer (2002)83 Annotate PropBank Arguments Gold-Standard Parses from TreeBank

AQUAINT Workshop – June 2003 Using Real Parses Arg IDRole A TreeBank Parse Charniak Parse Annotate PropBank Arguments Arg IDRole A TreeBank Parse Charniak Parse AnnotateThematic Roles

AQUAINT Workshop – June 2003 ID and Label ID and Annotate Thematic Roles Using Charniak Parse Top N Classification

AQUAINT Workshop – June 2003 Hard vs Soft Pruning Soft Pruning Train Null-vs-Role classifier on all data Prune constituents with P(Null) > 0.98 Train ova classifiers (incl Null) on remaining constituents Hard Pruning Train Null-vs-Role classifier on all data Make Null-vs-Role classification for each constituents Train ova classifiers (no Null) on role constituents

AQUAINT Workshop – June 2003 Segment & Classify with SVM Initial system used Charniak parser to segment –SVM classified segmented constituents Use SVM to segment and classify chunks Features: –Window of 5 words (+2,target,-2) –POS tags for words –Syntactic phrase position tags (B,I,O) –Path from word to target –Class assignments for previous words Assign Semantic phrase position tag to each word

AQUAINT Workshop – June 2003 SVM Chunking Parser Syntactic Parser Path Finder Chunker Active Passive Detector words path for each word POS tags word positions voice Target word detector target word input sentence Features

AQUAINT Workshop – June 2003 Example I But CC O CC VP->VBP say B A O analysts NNS B-NP NNS VP->VBP say B A B-agent IBM NNP B-NP VBP SBAR->S->NP->NNP say A A B-topic is AUX O VBP SBAR->S->VP->AUX say A A I-topic a DT B-NP VBP SBAR->S->VP->NP->DT say A A I-topic special JJ I-NP VBP SBAR->S->VP->NP->JJ say A A I-topic case NN I-NP VBP SBAR->S->VP->NP->NN say A A I-topic But analysts say IBM is a special case But [ AGENT analysts] [ TARGET say] [ TOPIC IBM is a special case] Word POS SPP Path Pr B/A V Class

AQUAINT Workshop – June 2003 SVM Chunking Parser II Features POS tagger Path Finder Yamcha Chunker Active Passive Detector words path for each word POS tags word positions voice Target word detector target word input sentence

AQUAINT Workshop – June 2003 Example II But_ CC [ NP analysts_ NNS ] ( VP say_ VBP ) [ NP IBM_ NNP ] ( VP is_ VBZ ) [ NP a_ DT special_ JJ case_ NN ] But CC O CC->NP->VP->VBP say B A O analysts NNS B-NP NNS->NP->VP->VBP say B A B-agent IBM NNP B-NPNNP->NP->VP->VBPsay A A B-topic is VBZ B-VPVBZ->VP->NP->VP->VBP say A A I-topic a DT B-NPDT->NP->VP->NP->VP->VBP say A A I-topic special JJ I-NP JJ->NP->VP->NP->VP->VBP say A A I-topic case NN I-NPNN->NP->VP->NP->VP->VBP say A A I-topic POS tagged & Chunked (only NP and VP) But analysts say IBM is a special case Word POS SPP Path Pr B/A V Class

AQUAINT Workshop – June 2003 Performance Train on only first 3000 sentences PropBank data Segment & Annotate Thematic Roles 21,000 sentences training 3000 sentences training SVM Baseline80/74 Chunker-179/7167/53 Chunker-259/44 Chunker-I Syntax features derived from Charniak parse Chunker-II Syntax features from syntactic SVM chunker

AQUAINT Workshop – June 2003 Summary and Future Work Project has shown continued improvement in semantic parsing Goals: –Improve accuracy through new features –Improve robustness to data sets by improving word sense robustness –Continue experiments without full syntactic parse –Apply to Question Answering